© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 12-RES-JB
    11. 3128
    Prev
    Next
    INDEX
    Explanations

    phrases related to politics and government actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    statements and phrases indicating the presence of actions or descriptions related to individuals and their situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ogun
    -0.86
    idate
    -0.83
    ossibility
    -0.79
    bernatorial
    -0.77
     Inventory
    -0.77
    ucc
    -0.77
    essim
    -0.76
    izons
    -0.76
    ocry
    -0.75
    =-=-=-=-
    -0.75
    POSITIVE LOGITS
     transforming
    1.22
     robbing
    1.20
     inflicting
    1.18
     exploiting
    1.18
     turning
    1.16
     forcing
    1.16
     injecting
    1.15
     destroying
    1.15
     stealing
    1.15
     harming
    1.14
    Activations Density 0.427%

    No Known Activations